© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 216001
    Prev
    Next
    INDEX
    Explanations

    listing provided courtesy

    np_acts-logits-general · gemini-2.5-flash-lite

    question clarification/scoping

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     I
    0.47
    า
    0.46
     (
    0.44
    ة
    0.44
     inefficient
    0.42
    รอ
    0.42
     •
    0.42
    <0xD9>
    0.41
    ším
    0.41
    ंपा
    0.40
    POSITIVE LOGITS
     বন্ধুর
    0.56
     mannit
    0.55
     Humidity
    0.55
     humides
    0.54
     মনোরম
    0.53
     увла
    0.52
    kommt
    0.52
     گیرد
    0.51
     বাড়ি
    0.50
    ഹ്ലാ
    0.50
    Activations Density 0.001%

    No Known Activations